© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40309
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uf
    -0.07
    apore
    -0.07
     now
    -0.07
    cents
    -0.07
    erras
    -0.07
    uyo
    -0.07
    apon
    -0.07
    缮åīį
    -0.07
    är
    -0.07
    ixin
    -0.06
    POSITIVE LOGITS
     whenever
    0.07
     Sunder
    0.07
     dönemde
    0.06
    cir
    0.06
    çļĦä¸Ģ个
    0.06
     Whenever
    0.06
     thiá»ĩn
    0.06
     Fulton
    0.06
    enburg
    0.06
     inv
    0.06
    Activations Density 0.021%

    No Known Activations